Training setting about rescan HOT 4 CLOSED

Hi there. I've been reading the paper and tried to understand the codes as well. Here is what I think.
First, the Rain800 contains the training dataset and the validation dataset. The folder named "test_syn" containing 100 images should be the validation dataset. So you could rename it to "val".
Then, you may need to download the Rain100H dataset(http://www.icst.pku.edu.cn/struct/Projects/joint_rain_removal.html). This is actually the testing dataset. After that, you may want to create a new folder named "test" under your dataset folder "rain". Then take 100 rainy images from the Rain100H and move them to the "test" folder.
I think that is all in terms of preparing the dataset. Hope it can help.

from rescan.

Hello,
when I was runing the codes as "test", that is: python main.py --action test
it raised one error like this:
2018-09-05 17:28:12,461 - INFO - set log dir as ../logdir
2018-09-05 17:28:12,461 - INFO - set model dir as ../models
Traceback (most recent call last):
File "main.py", line 229, in
run_test(args.model)
File "main.py", line 205, in run_test
for i, batch in enumerate(dt):
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 314, in next
batch = self.collate_fn([self.dataset[i] for i in indices]) ###
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 184, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in batch[0]}
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 184, in
return {key: default_collate([d[key] for d in batch]) for key in batch[0]}
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 173, in default_collate
return torch.stack([torch.from_numpy(b) for b in batch], 0)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 481 and 321 in dimension 2 at c:\new-builder_3\win-wheel\pytorch\aten\src\th\generic/THTensorMath.cpp:3616

Does anyone know how to fix this problem??

from rescan.

Hello,
when I was runing the codes as "test", that is: python main.py --action test
it raised one error like this:
2018-09-05 17:28:12,461 - INFO - set log dir as ../logdir
2018-09-05 17:28:12,461 - INFO - set model dir as ../models
Traceback (most recent call last):
File "main.py", line 229, in
run_test(args.model)
File "main.py", line 205, in run_test
for i, batch in enumerate(dt):
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 314, in next
batch = self.collate_fn([self.dataset[i] for i in indices]) ###
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 184, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in batch[0]}
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 184, in
return {key: default_collate([d[key] for d in batch]) for key in batch[0]}
File "C:\Users\pengx\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\utils\data\dataloader.py", line 173, in default_collate
return torch.stack([torch.from_numpy(b) for b in batch], 0)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 481 and 321 in dimension 2 at c:\new-builder_3\win-wheel\pytorch\aten\src\th\generic/THTensorMath.cpp:3616

Does anyone know how to fix this problem??

This bug arises from the usage of iter, and I just fix it.
Please refer to the latest repo.

from rescan.

Hi,
Could you tell me where can I download the original Rain800 dataset.
Thanks

from rescan.